Neuralangelo, a new AI model from Nvidia Research, uses AI to take two-dimensional video clips and turn them into detailed 3D graphics structures. With this tech, the researchers have been able to ...

Researchers have developed a new technique, called MonoCon, that improves the ability of artificial intelligence (AI) programs to identify three-dimensional (3D) objects, and how those objects relate ...

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now After several decades of hope, hype and ...

The metaverse is taking shape right now, and Nvidia has gone all in, introducing a robust set of tools to build it. But even for a graphics pioneer like Nvidia, rendering 3D worlds is a complicated ...

Penn researchers have developed a universal algorithm that allows 2D materials to retain mechanical strength after conversion into 3D structures. The team’s work takes inspiration from kirigami, an ...

A neural field network can create a continuous 3D model from a limited number of 2D images, and it does it without being trained on other samples. Researchers from the McKelvey School of Engineering ...

Open-source components based on universal scene description and Hydra were used to speed up iteration and model inspection in the Revit Tech Preview released on April 2. Turning a photograph or a scan ...